© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 7658
    Prev
    Next
    INDEX
    Explanations

    www website addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fts
    2.24
    znym
    2.18
     impi
    2.10
    حدة
    2.09
    ppes
    2.06
    ỉ
    2.01
    дного
    1.99
    zev
    1.98
    cosa
    1.97
    hrung
    1.90
    POSITIVE LOGITS
    t
    2.85
    ン
    2.63
    <0x80>
    2.49
    います
    2.20
     nutritious
    2.13
    收取
    2.12
    də
    2.09
    न
    2.08
    nX
    2.07
    r
    2.01
    Activations Density 0.007%

    No Known Activations